On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,051 papers · 148 categories

Trend · papers per month

count % of corpus

5 results for “cyber-intrusions”

Efficient GAN-based method for cyber-intrusion detectioncs.LG

Paper proposes an efficient GAN model for discrete cyber-intrusion detection.

problem Cyber-intrusion detection in systems with rare abnormal data.

method Generative adversarial network (GAN) with a specifically-designed loss function for discrete data.

result The proposed model outperforms state-of-the-art models on discrete datasets.

GAN cyber-intrusion discrete data anomaly detection performance improvement

2019-04-04abs ↗pdf ↗

Multi-centrality Graph Spectral Decompositions and their Application to Cyber Intrusion Detectioncs.SI

Many modern datasets can be represented as graphs and hence spectral decompositions such as graph principal component analysis (PCA) can be useful. Distinct from previous graph decomposition approaches based on subspace projection of a single topological feature, e.g., the Fiedler vector of centered graph adjacency mat…

2015-12-23abs ↗pdf ↗

On the Veracity of Cyber Intrusion Alerts Synthesized by Generative Adversarial Networkscs.LG

GANs generate realistic cyber-attack alerts with feature dependencies.

problem Challenges in creating realistic cyber-attack alert data.

method Used Generative Adversarial Networks (GANs) to learn complex data distributions.

result GANs successfully generate realistic alerts with feature dependencies.

GANs cyber-attack alerts feature dependencies Mutual Information conditional entropy

2019-08-03abs ↗pdf ↗

MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networkscs.LG

MAD-GAN detects anomalies in multivariate time series data using GANs.

problem Complex multivariate time series data requires better anomaly detection methods.

method Unsupervised anomaly detection using Generative Adversarial Networks (GANs).

result MAD-GAN effectively detects anomalies in real-world CPS systems.

anomaly detection GANs multivariate time series cyber-intrusions smart buildings

2019-01-15abs ↗pdf ↗

Change Detection in Noisy Dynamic Networks: A Spectral Embedding Approachcs.LG

Novel method detects changes in noisy dynamic networks.

problem Change detection in noisy dynamic networks with sparsity and degree heterogeneity.

method Adapted Procrustes analysis to embedded points for vertices in spectral embedding.

result CDP successfully detects various types of vertex-based changes.

change detection spectral embedding dynamic networks Procrustes analysis sparsity

2019-10-05abs ↗pdf ↗